Keynote: Machine Learning and the Evaluation of Forensic Evidence
Presentation Type
Keynote
Abstract
The emergence of DNA analysis as an effective forensic tool in the 1990s was a revelation, in that for the first time it was possible to quantify the degree of association between a crime scene sample and a suspect. It also had the effect of shining a light on other forensic practices, most of which lack the rigorous and widely accepted scientific foundations of DNA profiling and for which error rates are largely unknown. In the US criminal justice system, jurors choose between two competing hypothesis: the suspect is the source of the evidence found at the crime scene or is not. We discuss how statistical learning algorithms can help address the question of the source of the evidence, and use firearms examination as an illustration. Can we tell whether the defendant’s gun fired the bullet recovered from the scene of the crime?
Start Date
2-11-2020 8:30 AM
End Date
2-11-2020 9:15 AM
Keynote: Machine Learning and the Evaluation of Forensic Evidence
The emergence of DNA analysis as an effective forensic tool in the 1990s was a revelation, in that for the first time it was possible to quantify the degree of association between a crime scene sample and a suspect. It also had the effect of shining a light on other forensic practices, most of which lack the rigorous and widely accepted scientific foundations of DNA profiling and for which error rates are largely unknown. In the US criminal justice system, jurors choose between two competing hypothesis: the suspect is the source of the evidence found at the crime scene or is not. We discuss how statistical learning algorithms can help address the question of the source of the evidence, and use firearms examination as an illustration. Can we tell whether the defendant’s gun fired the bullet recovered from the scene of the crime?